Manifold Alignment Aware Ants: A Markovian Process for Manifold Extraction

The presence of manifolds is a common assumption in many applications, including astronomy and computer vision. For instance, in astronomy, low-dimensional stellar structures, such as streams, shells, and globular clusters, can be found in the neighborhood of big galaxies such as the Milky Way. Since these structures are often buried in very large data sets, an algorithm, which can not only recover the manifold but also remove the background noise (or outliers), is highly desirable. While other works try to recover manifolds either by pushing all points toward manifolds or by downsampling from dense regions, aiming to solve one of the problems, they generally fail to suppress the noise on manifolds and remove background noise simultaneously. Inspired by the collective behavior of biological ants in food-seeking process, we propose a new algorithm that employs several random walkers equipped with a local alignment measure to detect and denoise manifolds. During the walking process, the agents release pheromone on data points, which reinforces future movements. Over time the pheromone concentrates on the manifolds, while it fades in the background noise due to an evaporation procedure. We use the Markov chain (MC) framework to provide a theoretical analysis of the convergence of the algorithm and its performance. Moreover, an empirical analysis, based on synthetic and real-world data sets, is provided to demonstrate its applicability in different areas, such as improving the performance of t-distributed stochastic neighbor embedding (t-SNE) and spectral clustering using the underlying MC formulas, recovering astronomical low-dimensional structures, and improving the performance of the fast Parzen window density estimator.

Estimating the Gait Speed of Older Adults in Smart Home Environments

Mobility is one of the key performance indicators of the health condition of older adults. One important parameter is the gait speed. The mobility is usually assessed under the supervision of a professional by standardised geriatric assessments. Using sensors in smart home environments for continuous monitoring of the gait speed enables physicians to detect early stages of functional decline and to initiate appropriate interventions. This in combination with a floor plan smart home sensors were used to calculate the distance that a person walked in the apartment and the inertial measurement unit data for estimating the actual walking time. A Gaussian kernel density estimator was applied to the computed values and the maximum of the kernel density estimator was considered as the gait speed. The proposed method was evaluated on a real-world dataset and the estimations of the gait speed had a deviation smaller than $$0.10 \, \frac{\mathrm{m}}{\mathrm{s}}$$ 0.10 m s , which is smaller than the minimal clinically important difference, compared to a baseline from a standardised geriatrics assessment.

Sparse Density Estimation with Measurement Errors

This paper aims to estimate an unknown density of the data with measurement errors as a linear combination of functions from a dictionary. The main novelty is the proposal and investigation of the corrected sparse density estimator (CSDE). Inspired by the penalization approach, we propose the weighted Elastic-net penalized minimal ℓ2-distance method for sparse coefficients estimation, where the adaptive weights come from sharp concentration inequalities. The first-order conditions holding a high probability obtain the optimal weighted tuning parameters. Under local coherence or minimal eigenvalue assumptions, non-asymptotic oracle inequalities are derived. These theoretical results are transposed to obtain the support recovery with a high probability. Some numerical experiments for discrete and continuous distributions confirm the significant improvement obtained by our procedure when compared with other conventional approaches. Finally, the application is performed in a meteorology dataset. It shows that our method has potency and superiority in detecting multi-mode density shapes compared with other conventional approaches.

One-Class Model for Fabric Defect Detection

An automated and accurate fabric defect inspection system is in high demand as a replacement for slow, inconsistent, error-prone, and expensive human operators in the textile industry. Previous efforts focused on certain types of fabrics or defects, which is not an ideal solution. In this paper, we propose a novel one-class model that is capable of detecting various defects on different fabric types. Our model takes advantage of a well designed Gabor filter bank to analyze fabric texture. We then leverage an advanced deep learning algorithm, autoencoder, to learn general feature representations from the outputs of the Gabor filter bank. Lastly, we develop a nearest neighbor density estimator to locate potential defects and draw them on the fabric images. We demonstrate the effectiveness and robustness of the proposed model by testing it on various types of fabrics such as plain, patterned, and rotated fabrics. Our model also achieves a true positive rate (a.k.a recall) value of 0.895 with no false alarms on our dataset based upon the Standard Fabric Defect Glossary.

Refining and evaluating a Horvitz– Thompson-like stand density estimator in individual tree detection based on airborne laser scanning

Horvitz--Thompson-like stand density estimation is a method for estimating the stand density from tree crown objects extracted from airborne laser scanning data through individual tree detection. The estimator is based on stochastic geometry and mathematical morphology of the (planar) set formed by the detected tree crowns. This set is used to approximate the detection probabilities of trees. These probabilities are then used to calculate the estimate. The method includes a tuning parameter, which needs to be known to apply the method. We present a refinement of the method to allow more general detection conditions than the previous papers and present and discuss the methods for estimating the tuning parameter of the estimator using a functional $k$-nearest neighbors method. We test the model fitting and prediction in two spatially separate data sets and examine the plot-level accuracy of estimation. The estimator produced a $13$\% lower RMSE than the benchmark method in an external validation data set. We also analyze the effects of similarity and dissimilarity of training and validation data to the results.

Landscape Characteristics Influence Ranging Behavior of Asian Elephants at The Human-Wildlands Interface in Myanmar

ContextAsian elephant numbers are declining across much of their range driven largely by serious threats from land use change resulting in habitat loss and fragmentation. Myanmar, holding critical range for the species, is undergoing major developments due to recent sociopolitical changes. To effectively manage and conserve the remaining populations of endangered elephants in the country, it is crucial to understand their ranging behavior.ObjectivesOur objectives were to (1) estimate the sizes of dry, wet and annual ranges of free ranging elephants in Myanmar; and quantify the relationship between dry season (the period when human-elephant interactions are the most likely to occur) range size and configurations of agriculture and natural vegetation within the range, and 2) evaluate how percentage of agriculture within dry core range (50% AKDE range) of elephants relates to their daily distance traveled.MethodsWe used autocorrelated kernel density estimator (AKDE) based on a continuous-time movement modeling (ctmm) framework to estimate dry season (26 ranges from 22 different individuals), wet season (12 ranges from 10 different individuals), and annual range sizes (8 individuals), and reported the 95%, 50% AKDE, and 95% Minimum Convex Polygon (MCP) range sizes. We assessed how landscape characteristics influenced range size based on a broad array of 48 landscape metrics characterizing aspects of vegetation, water, and human features and their juxtaposition in the study areas. To identify the most relevant landscape metrics and simplify our candidate set of informative metrics, we relied on exploratory factor analysis and Spearman’s rank correlation coefficient. Based on this analysis we adopted a final set of metrics into our regression analysis. In a multiple regression framework, we developed candidate models to explain the variation in AKDE dry season range sizes based on the previously identified, salient metrics of landscape composition. ResultsElephant dry season ranges were highly variable averaging 792.0 km2 and 184.2 km2 for the 95% and 50% AKDE home ranges, respectively. We found both the shape and spatial configuration of agriculture and natural vegetation patches within an individual elephant’s range play a significant role in determining the size of its range. We also found that elephants are moving more (larger energy expenditure) in ranges with higher percentages of agricultural area.ConclusionOur results provide baseline information on elephant spatial requirements and the factors affecting them in Myanmar. This information is important for advancing future land use planning that takes into account space-use requirements for elephants. Failing to do so may further endanger already declining elephant populations in Myanmar and across the species’ range.

Mapping of mangrove forest tree density using SENTINEL 2A satelit image in remained natural mangrove forest of Sumatra eastern coastal

The mangrove ecosystem in Forest Managemen Unit - VII (FMU) Sumatera Utara is a natural forest. FMU has not managed and utilizes mangrove forests optimally. It can open up opportunities for illegal loggers and trigger damage to these natural ecosystems. This condition requires prevention and mitigation so that severe damage to mangrove forests does not occur. This study aims to determine the relationship between vegetation index and mangrove density in the field and map the mangrove density distribution based on the image vegetation index value. The density distribution mapping was carried out by compiling a vegetation density estimator model NDVI, GNDVI, and TVI as independent variables. Correlation test and regression analysis between the vegetation index value (NDVI, GNDVI, and TVI) to the number of trees per unit area. The distribution model for the density of mangrove stands was chosen based on the coefficient of determination (R2). The study resulted from NDVI selected as the vegetation index used to map the distribution of mangrove density with a Pearson correlation coefficient (R) of 0.738. The selected model is Y = 2.48e2.8667x, which is an exponential equation with a coefficient of determination (R2) of 61.3%. Based on this model, the distribution of mangrove density has the lowest density reaching 400, and the highest density is 2,200 trees per hectare

Fourier Ring Correlation and Anisotropic Kernel Density Estimation Improve Deep Learning Based SMLM Reconstruction of Microtubules

Single-molecule super-resolution microscopy (SMLM) techniques like dSTORM can reveal biological structures down to the nanometer scale. The achievable resolution is not only defined by the localization precision of individual fluorescent molecules, but also by their density, which becomes a limiting factor e.g., in expansion microscopy. Artificial deep neural networks can learn to reconstruct dense super-resolved structures such as microtubules from a sparse, noisy set of data points. This approach requires a robust method to assess the quality of a predicted density image and to quantitatively compare it to a ground truth image. Such a quality measure needs to be differentiable to be applied as loss function in deep learning. We developed a new trainable quality measure based on Fourier Ring Correlation (FRC) and used it to train deep neural networks to map a small number of sampling points to an underlying density. Smooth ground truth images of microtubules were generated from localization coordinates using an anisotropic Gaussian kernel density estimator. We show that the FRC criterion ideally complements the existing state-of-the-art multiscale structural similarity index, since both are interpretable and there is no trade-off between them during optimization. The TensorFlow implementation of our FRC metric can easily be integrated into existing deep learning workflows.

A Fast-Converging Kernel Density Estimator for Dispersion in Horizontally Homogeneous Meteorological Conditions

Kernel smoothers are often used in Lagrangian particle dispersion simulations to estimate the concentration distribution of tracer gasses, pollutants etc. Their main disadvantage is that they suffer from the curse of dimensionality, i.e., they converge at a rate of 4/(d+4) with d the number of dimensions. Under the assumption of horizontally homogeneous meteorological conditions, we present a kernel density estimator that estimates a 3D concentration field with the faster convergence rate of a 1D kernel smoother, i.e., 4/5. This density estimator has been derived from the Langevin equation using path integral theory and simply consists of the product between a Gaussian kernel and a 1D kernel smoother. Its numerical convergence rate and efficiency are compared with that of a 3D kernel smoother. The convergence study shows that the path integral-based estimator has a superior convergence rate with efficiency, in mean integrated squared error sense, comparable with the one of the optimal 3D Epanechnikov kernel. Horizontally homogeneous meteorological conditions are often assumed in near-field range dispersion studies. Therefore, we illustrate the performance of our method by simulating experiments from the Project Prairie Grass data set.

Socio-Epidemiological Features and Spatial Distribution of Malaria in an Area under Mining Activity in the Brazilian Amazon Region

Malaria is an acute febrile infectious disease that represents an important public health problem in the Brazilian amazon region. The present study described the socio-epidemiological and spatial characteristics of malaria in a population from the Tapajós mining areas, Pará, Brazilian Amazon. A cross-sectional study, including individuals from Itaituba city, an area under mining activity influence, was conducted. The geographic coordinates were obtained in the field using the Global Positioning System (GPS) Garmin 78csx; for spatial analysis, we used the Kernel Density Estimator with the application of scanning statistics with the SaTScan software. Of the 908 individuals, 311 were positive for malaria. Most of the malaria cases were associated with male individuals, gold miners and with a monthly income of 4-6 salaries. Binary logistic regression analysis demonstrated that gold miners were nearly five times more likely to acquire malaria. In addition, a context of risk for sexually transmitted infections, substance abuse and poor support conditions was observed, worsening the healthcare scenario in this endemic area for malaria. The spatial distribution of malaria cases is irregular in the municipality with hotspot areas located in the Amana Flona that coincide with areas of illegal mining and high human mobility. Finally, the presented socio-epidemiological and spatial distribution data may aid in the development of more effective control measures for malaria in the area.